174 points by lyra1337 3 days ago | 27 comments | View on ycombinator
chriddyp 2 days ago |
jauntywundrkind 2 days ago |
224b params. 320b for glm-5.3-flash. 180b for qwen3.8 flash next. 552b for DeepSeek flash v4.1 but that has way stronger performance, for 4x+ the price.
Also, they do mention at the end that yes they are going to open the weights here.
ddxv 2 days ago |
Lately I let myself drift into using Terra and some other mildly 'expensive' models, but really I think the sweet spot for me is cheap and fast.
thesurlydev 2 days ago |
DeathArrow 2 days ago |
tkslucas 2 days ago |
syntaxing 2 days ago |
wsxiaoys 2 days ago |
More results: https://sketchagent.dev/#/a/hy4-flash
DeathArrow 2 days ago |
Even a $10 Open Code plan will get you far because it will hit cache a lot if you use a matching harness.
Rodmine 2 days ago |
Kuyawa 2 days ago |
throwa356262 1 day ago |
Eden reports 40tps for hy4: https://www.edenai.co/models/hy4
And error rate is not insignificant according to Openrouter: https://openrouter.ai/tencent/hy4
ketzu 2 days ago |
Maybe Hy4 flash will at least not also be expensive while breaking on me.
edtechdev 2 days ago |
trilogic 2 days ago |
vcryan 2 days ago |
undefined 2 days ago |
undefined 3 days ago |
paramseast 2 days ago |
TheJCDenton 2 days ago |
scottchiefbaker 2 days ago |
italiansolider 2 days ago |
Beat out GPT-6 Luna on the low end of cheap + accurate. Only cost $0.13 to answer 43 data analytics questions (compared to ~$20 on the high end of expensive frontier models).
Once the open the weights, Hy4 Flash and regular Hy4 will be the only two open models on the frontier in the exam I've been running.
[1] https://plotly.com/blog/hy4-flash-plotly-data-analytics-benc...